audit 2026-10-18: new incident page (omniroute-1 503 resource pressure, 9 calls / 7 jobs), fleet re-verified 28 jobs / 25 enabled / 8 non-clean, Mosquito Tracker removed, radar bot token dead

This commit is contained in:
hermes-audit
2026-10-18 00:41:38 +08:00
parent 76de919e6a
commit 4137dd6945
7 changed files with 276 additions and 23 deletions
+4 -3
View File
@@ -1,6 +1,6 @@
# Anthony's Systems Wiki
> Operational knowledge for Anthony's agents, infrastructure,
> model routing and automation. Last updated: 2026-10-16
> model routing and automation. Last updated: 2026-10-18
>
> ⚠ **Two Proxmox hosts exist — always qualify a guest with its host.** A second unclustered
> hypervisor, `m93p` (`100.104.51.98`, PVE 9.2.0), was discovered during the 2026-10-14 stocktake.
@@ -33,10 +33,11 @@
### Integrations
- [[systems/messaging-integrations]] — Telegram, Discord, email, Slack, etc.
- [[systems/scheduled-tasks]] — **29 cron jobs (26 enabled, 3 disabled)**; **12 carry a non-clean `last_status`** as of 2026-10-16 00:1x — the **`omniroute-1` connection-refused storm (2026-10-14 → 10-15)** cost **24 model-call failures across 12 jobs** and blanked ~34 h of digests; **all 18 model-calling jobs sit on `custom:omni-101` with no failover**. See [[incidents/2026-10-14-omniroute-node-connection-refused-storm]]. Prior audit: **4 carried a non-clean `last_status`** as of 2026-10-14 00:15. **The clean streak broke on 2026-10-13: `167 completed` / 1 `failed`**, after 10-12 finalised `175 / 0` (10-11 `172 / 0`, 10-10 `175 / 0`) — `1a8e90ea2271` (wiki-stocktake-maintenance, 03:00) hit `HTTP 404: No active credentials for provider: opencode`, its **third failure in six days**, so **open incidents rose 2 → 3**. Two rows cleared: `fad5a86979d4` (10-12 03:05), `dca8482e4f76` (10-13 07:02). The DHL monitor `62619aa6bcb3` was **retired** on 2026-10-10. ⚠ A green cron row is not proof of delivery: GitHub Trending Radar's Telegram token is revoked (`getMe` → 401) while the row stays green — it next runs Mon 09:00. See [[incidents/2026-10-09-cron-provider-timeout-storm]]
- [[systems/skills-index]] — Installed skills inventory (**346 skills / 70 categories**; regenerated daily by the 03:00 stocktake job). Note: 347 `SKILL.md` files exist on disk — the generator de-dups one nested duplicate, see [[systems/scheduled-tasks]]. ⚠ The **2026-10-13** regeneration wrote the file but the stocktake job died before committing, so the artifact sat stranded until the 2026-10-14 audit committed it (date-only change: `updated`/`verified_on` 10-12 → 10-13).
- [[systems/scheduled-tasks]] — **28 cron jobs (25 enabled, 3 disabled)**; **8 carry a non-clean `last_status`** as of 2026-10-18 00:3x — down from 12. The **`omniroute-1` 503 resource-pressure window (2026-10-16 08:00 → 10-17 03:00)** cost **9 model-call failures across 7 jobs** and was followed by a clean 10-17 06:00 → 10-18 window; the Mosquito Tracker was removed (29 → 28 jobs). See [[incidents/2026-10-16-omniroute-503-resource-pressure]]. Prior incident: the **connection-refused storm (2026-10-14 → 10-15)** — **24 model-call failures across 12 jobs** and ~34 h of digests blanked. **All 18 model-calling jobs still sit on `custom:omni-101` with no failover.**
- [[systems/skills-index]] — Installed skills inventory (**346 skills / 70 categories**; regenerated daily by the 03:00 stocktake job). Note: 347 `SKILL.md` files exist on disk — the generator de-dups one nested duplicate, see [[systems/scheduled-tasks]]. ⚠ **2026-10-17** stocktake slot failed (`HTTP 503`), so `freshness-20261017.txt` is missing and the index is stamped **10-16**; the **10-18 03:00** slot closes it. ⚠ The **2026-10-13** regeneration wrote the file but the stocktake job died before committing, so the artifact sat stranded until the 2026-10-14 audit committed it (date-only change: `updated`/`verified_on` 10-12 → 10-13).
## Incidents
- [[incidents/2026-10-16-omniroute-503-resource-pressure]] — **OmniRoute's second failure mode, 2026-10-16 → 10-17:** `omniroute-1` load-shed model calls with **`HTTP 503 … resource pressure`** — **9 model calls across 7 jobs** over ~19 h, while `/api/health` stayed `200 ok` and `/v1/models` stayed `401`. **Self-cleared** (last 503 10-17 03:00:28; 10-17 closed 162 / 5, 10-18 so far 7 / 0). 9 incidents opened, 6 closed; **8 open** overall, and the ledger tags **7 of the 9 `failure_type: unknown`**. **Single-node topology still open.**
- [[incidents/2026-10-14-omniroute-node-connection-refused-storm]] — **Fleet-wide 34-hour cron blackout, 2026-10-14 → 10-15:** `omniroute-1` (`100.78.63.20:20128`, provider `custom:omni-101`) refused TCP connections, so **every model-calling cron job failed on every slot** — 24 genuine model-call failures across 12 jobs (+12 derivative watchdog reds), and all digests for ~34 h were silently suppressed. **All 18 enabled model-calling jobs ride this one node with no failover.** Recovered 10-15 22:01 (resolved)
- [[incidents/2026-10-09-cron-provider-timeout-storm]] — Fleet-wide provider timeout storm: 15 failed executions across 10 jobs on 2026-10-09, all `RuntimeError: Request timed out.` on the aliases behind `custom:omni-101`, 00:00 → 15:00 AWST; **11 of its 12 incidents are now closed** (five on 2026-10-10, the last hold-out `dca848_23fcd2b18aaa` on 2026-10-12 07:33:41). **1 remains `alerted`** — `1b23c042e17d`, the weekly Friday job, which cannot clear before its next slot (Fri 2026-10-16 08:00)
- [[incidents/2026-10-09-memory-recall-relevance]] — Recall relevance: a stale conversational episode outranked current-state facts on an open question; capture and vectorisation verified healthy, the ranking fix was never persisted in config (unresolved)